Extract evaluation results from README

This commit adds structured evaluation results to the model card. The results are formatted using the model-index specification and will be displayed in the model card's evaluation widget.

README.md

@@ -6,6 +6,30 @@ license: mit
 pipeline_tag: image-text-to-text
 tags:
 - multimodal
+model-index:
+- name: Fara-7B
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: Benchmarks
+      type: benchmark
+    metrics:
+    - name: WebVoyager
+      type: webvoyager
+      value: 73.5
+    - name: Online-M2W
+      type: online_m2w
+      value: 34.1
+    - name: DeepShop
+      type: deepshop
+      value: 26.2
+    - name: WebTailBench
+      type: webtailbench
+      value: 38.4
+    source:
+      name: Model README
+      url: https://huggingface.co/microsoft/Fara-7B
 ---
 
 # Fara-7B: An Efficient Agentic Model for Computer Use